Opus 5 max thinking reportedly underperforms xhigh on 20–30% of benchmarks
keunwoochoi · x · 2026-07-25
A reply to a discussion of Opus 5 notes that Opus 4.8 does not show the same issue and suggests the behavior may indicate a rushed release.
The quoted observation underneath says that in roughly 20–30% of reported benchmarks, Opus 5 max thinking performs worse than xhigh. The surprising part is that more thinking and more test-time compute would normally be expected to improve results, so the benchmark drops may point to either an emergent issue in smaller models or a post-training problem.
Related event: Opus 5 Coding Paradox: Higher Reasoning Leads to Lower Scores(13 posts)→
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27